Machine learning techniques to construct detailed phase diagrams for skyrmion systems

F. A. GÓMEZ ALBARRACÍN; H. D. ROSALES

PHYSICAL REVIEW B

AMER PHYSICAL SOC

Lugar: New York; Año: 2022

1098-0121

Recently, there has been an increased interest in the application of machine learning (ML) tech-niques to a variety of problems in condensed matter physics. In this regard, of particular significanceis the characterization of simple and complex phases of matter. Here, we use a ML approach toconstruct the full phase diagram of a well known spin model combining ferromagnetic exchangeand Dzyaloshinskii-Moriya (DM) interactions where topological phases emerge. At low tempera-tures, the system is tuned from a spiral phase to a skyrmion crystal by a magnetic field. However,thermal fluctuations induce two types of intermediate phases, bimerons and skyrmion gas, whichare not as easily determined as spirals or skyrmion crystals. We resort to large scale Monte Carlosimulations to obtain low temperature spin configurations, and train a convolutional neural network(CNN), taking only snapshots at specific values of the DM couplings, to classify between the dif-ferent phases, focusing on the intermediate and intricate topological textures. We then apply theCNN to higher temperature configurations and to other DM values, to construct a detailed mag-netic field-temperature phase diagram, achieving outstanding results. We discuss the importance ofincluding the disordered paramagnetic phases in order to get the phase boundaries, and finally, wecompare our approach with other ML algorithms.